metadata
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
- generated_from_trainer
datasets:
- superb
metrics:
- accuracy
model-index:
- name: wav2vec2-base-finetuned-ks-unbalanced
results:
- task:
name: Audio Classification
type: audio-classification
dataset:
name: superb
type: superb
config: ks
split: validation
args: ks
metrics:
- name: Accuracy
type: accuracy
value: 0.9779346866725508
wav2vec2-base-finetuned-ks-unbalanced
This model is a fine-tuned version of facebook/wav2vec2-base on the superb dataset. It achieves the following results on the evaluation set:
- Loss: 0.1805
- Accuracy: 0.9779
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 3e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.2449 | 1.0 | 199 | 1.1639 | 0.6731 |
| 0.5926 | 2.0 | 399 | 0.4796 | 0.9256 |
| 0.3655 | 3.0 | 599 | 0.2651 | 0.9737 |
| 0.2644 | 4.0 | 799 | 0.1970 | 0.9766 |
| 0.2425 | 4.98 | 995 | 0.1805 | 0.9779 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3